Autoregressive transformers follow power-law scaling laws for cross-entropy loss with nearly universal exponents relating optimal model size to compute budget across four domains.
Multimodal transformer for unaligned multimodal language sequences
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2020 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Scaling Laws for Autoregressive Generative Modeling
Autoregressive transformers follow power-law scaling laws for cross-entropy loss with nearly universal exponents relating optimal model size to compute budget across four domains.